INDEX
    Explanations

    expressions of desire or intent

    New Auto-Interp
    Negative Logits
    InSection
    -0.41
     CBC
    -0.40
     McGraw
    -0.40
     Groves
    -0.39
    egli
    -0.39
    ReadLine
    -0.37
     foolish
    -0.36
     technique
    -0.35
    ..\..\
    -0.35
    DG
    -0.35
    POSITIVE LOGITS
     want
    1.44
    want
    1.41
     WANT
    1.40
     Want
    1.36
    Want
    1.35
    wants
    1.29
     wants
    1.25
     Wants
    1.23
     wanting
    1.22
    WANT
    1.21
    Act Density 0.196%

    No Known Activations